# The Long Tail, Not the Front Page: Cold-Start Prediction of Crowd Highlight Salience

arXiv: https://arxiv.org/abs/2606.11654 · HTML: https://mlsanity.com/paper/2606.11654/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 12 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Builds on (most cited first, 7 of 7)

- [Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracy](https://mlsanity.com/paper/2402.19379/) (2024)
- [A Re-visit of the Popularity Baseline in Recommender Systems](https://mlsanity.com/paper/2005.13829/) (2020)
- [Behavioral Analysis of Information Salience in Large Language Models](https://mlsanity.com/paper/2502.14613/) (2025)
- [Personal Salience: Highlighting Is Social, but Individuality Lives in Selection](https://mlsanity.com/paper/2606.09024/) (2026)
- [Selection, Not Salience: The Shape and Limits of Personalization in Social Highlighting](https://mlsanity.com/paper/2606.10398/) (2026)
- [Catching Attention with Automatic Pull Quote Selection](https://mlsanity.com/paper/2005.13263/) (2020)
- [Disentangling Answer Engine Optimization from Platform Growth: A Log-Based Natural Experiment on ChatGPT Referral Traffic](https://mlsanity.com/paper/2606.04362/) (2026)

## Built on by (most cited first, 3 of 3)

- [Floor, Ceiling, and the Fusion Gap: How Much of Crowd Reading Attention Can Machines Predict?](https://mlsanity.com/paper/2608.01704/) (2026)
- [Trait, Not State: The Durability of Reading Identity in Social Highlighting](https://mlsanity.com/paper/2606.12904/) (2026)
- [More Reader Data or a Better Teacher? Updating a Model of Crowd Highlights in Late 2026](https://mlsanity.com/paper/2610.17768/) (2026)

## Abstract (arXiv)

A social highlighter's most useful signal -- which passages a crowd of readers marks -- exists only for documents people have already read. Can the aggregate crowd salience of a document be predicted from its text before its marks accumulate? Prior work on this data found that zero-shot language models recover highlight locations worse than a trivial lead (position) baseline, so we ask whether a model trained on the highlight corpus can beat that baseline. Using a pre-registered ladder of models and a by-document cluster bootstrap, we find a small but robust edge: a logistic ranker over sentence embeddings and positional/contextual features beats the lead baseline by +0.044 average precision (95% CI [+0.029, +0.058]; clears a pre-registered margin delta=0.03 in 97% of resamples, and stable across pipeline re-runs). Two unsupervised extractive baselines (centroid, LexRank-style centrality) lose to lead, and the trained model beats them by +0.108, so the edge is not recovered by generic unsupervised proxies -- it reflects learning from real reader marks. In product terms, precision@3 rises from 0.25 to 0.39 (+55% relative) and the model beats lead on 69% of documents. An ablation attributes the edge to the raw embedding (+0.014) and training augmentation (+0.010), each with a positive CI. The edge is not a temporal-generalization failure, and we find no evidence that content drift or near-duplicate leakage explains it. A standardized regression shows the advantage is governed mainly by document popularity (lower popularity, larger edge) and by label reliability. It nearly vanishes only on the most popular content; there it is the lead baseline that strengthens, not the model that weakens. Because our evaluation conditions on documents that eventually accumulated readers, these results are a retrospective cold-start simulation.